【導讀】的導航理念，并且這也在不久要實現(xiàn)的個人導航系統(tǒng)中占據(jù)重要的位置。戰(zhàn)，我們就有理由自命不凡了。在這里，我們將講解從已存在的GIS數(shù)據(jù)庫中獲。因為這些數(shù)據(jù)庫大多數(shù)沒有包含建筑物的高度和視圖信息，我們將展示這些信息怎樣從激光掃描數(shù)據(jù)中分離出來。以在任何樣式的汽車中找到導航系統(tǒng)。他們是相對復雜和成熟的系統(tǒng)可以以數(shù)字。地圖，行駛方向圖形，以及行駛中的聲音信息提供路線導航。航的大量地圖的提供，快速算路以及可靠的路線導航。然而，傳送這些信息的原始概念并沒有得到較大的改善。沿路中一系列的可識別可記憶的的圖像的提供。我們依照下列各項的方式，對于任何的觀察點的位置和觀看方向定義給予。為駕駛者的視野。固定方位被獲得。的光線在物體空間中被追蹤并且用DSM決定交集。對于每次擊中，對應的物體。底部到頂端被有效率地計算,向逐漸增加的物體空間進軍。道路標記唯一表示的適當物體。在那之后，僅僅是基于路標的行使指示還存在，這些是行使指示可能

　　

【正文】 ich allows to separate tree canopy and ground (Kraus and Rieger,1999). The main problem is how to extract symbolic information about manmade structures from laser scanner datasets, possibly bined with aerial or terrestrial images. Especially, the automatic generation of city models has been and still is an intense research field, the discussion of which is beyond the scope of this paper. The reader is referred to the excellent proceedings of the “Ascona workshops” on this topic (Gr168。un et al., 1995, Gr168。un et al., 1997,Baltsavias et al., 2021). However, there is still substantial research effort necessary until highly automated object extraction systems working reliably bee available. On the other hand, threedimensional object information is still far from being mon in today’s existing GIS databases. In consequence, in this paper we consider using twodimensional GIS databases in bination with laser scanner DSMs on an iconic level, without explicitly reconstructing the threedimensional shape of the objects as separate entities. Figure 3 shows an example of the data sources used, which is a DSM from laser scanning, regularized to a 1 m grid, the street geometry represented by center lines from a GDF data set, and the outline of buildings from a cadastral map. Figure3:Laser scan 中英文資料 5 CONCLUSION AND OUTLOOK In this paper, we have outlined how landmarks can be extracted and evaluated using existing GIS and laser scanning data. As for the extraction, we have investigated two different methods based on data mining to reveal prominent buildings. In order to evaluate the usefulness for navigation instructions, we used a visibility analysis based on DSM data from laser scanning. Both data mining procedures have still to be tested with real data sets. The results will verify if they lead to appropriate landmarks in the real world. In addition, the analysis process has to be extended to different object types (traffic constructions, parks, sporting facilities, etc.) extracted for example from ATKIS data. Methods for data preprocessing of different object types and categories, and problems when different data mining algorithms are applied to the same data set, have to be investigated. The reliability of the extracted landmarks has to be determined by a quality measure to avoid ambiguous landmarks misleading the user. More routedependent aspects to determine real landmarks have to be investigated: The influence of the users moving direction and visibility on the quality of landmarks. As we only used the “virtual image size” to rate an object’s visibility, there is much room for improvement. For example, from the virtual image, one can also obtain information on the distance, if the object is sticking out behind another, closer object, and if it is part of the silhouette. First pulse laser scan measurements could be integrated to get a better approximation for the occlusion caused by trees. The DSM could also be used to feed additional information to the extraction, for example, small towers sticking out behind a larger building could be identified. The implementation of the visibility tracking could also use equidistant time sampling instead of space sampling, based on assumed vehicle speeds in the vicinity of intersections. Finally, it would be interesting to investigate to what extend POI’s already existent in GDF datasets could be used for the visibility analysis.